25. 25
PaintsChainer (#PaintsChainer)
Neural network colorize line arts.
Released Jan. 2017, and already painted about one
million line images
http://free-illustrations.gatag.net/2014/01/10/220000.html
Taizan Yonetsuji
60. 60
GAN 敵対的生成モデル
z
x = G(z)
x
次の手順でxを生成する
(1) z 〜 U(0, I)でサンプリングする
(2) x = G(z)を計算する
最後にサンプリング
がないことに注意p(z)がGaussianでなく
一様分布Uを使うのも特徴
高次元の一様分布の場合
隅が離れた表現を扱える
61. 61
GAN 敵対的生成モデルの学習
偽物かを判定するD(x)を用意
— 本物なら1, 偽物なら0を返す
Dは上式を最大化するように学習し
Gは最小化するように学習する
— この学習はうまく進めば
∫p(z)G(z)dz=P(x), D(x)=1/2という
均衡解にたどり着ける
z
x'
x = G(z)
{1(本物), 0(偽物)}
y = D(x)
x
78. 78
参考文献
[Nguyen+ 2017] “The loss surface of deep and wide neural
networks”, Q. Nguyen, and et al., arXiv:1704.08045
[Mandt+ 2017] “Stochastic Gradient Descent as Approximate
Bayesian Inference”, S. Mandt, and et al., arxiv
[Lin + 16] “Why does deep and cheap learning work so well”,
H W. Lin, and et al., arXiv1708.08226
[Karras+ 17] Progressive Growing of GANs for Improved
Quality, Stability, and Variation, T. Karras and et al.,
arXiv:1710.10196
[Pathak+ 2017] Curiosity-driven Exploration by Self-
supervised Prediction, ICML 2017, D. Pathak and et. al.
79. 79
[Kingma+ 14] ”Auto-Encoding Variational Bayes”, D. P.
Kingma and et al., ICLR 2014
[Higgins+ 17] “beta-VAE: Learning Basic Visual Concepts
with a Constrained Variational Framework”, I. Higgins and et
al., ICLR 2017
[Zhao+ 17] "Learning Hierarchical Features from Generative
Models”, S. Zhao and et al., ICML 2017
[Goodfellow+ 14] “Generative Adversarial Nets”, I.
Goodfellow, and et al., NIPS 2014
[Arjovsky+ 17a] ”Towards principled methods for training
generative adversarial networks”, M. Arjovsky, and et al,
arXiv:1701.04862
[Arjovsky+ 17b] “Wasserstein Generative Adversarial
Networks”, M. Arjovsky, and et al., ICML 2017
[Pathak+ 17] Curiosity-driven Exploration by Self-supervised
Prediction, D. Pathak and et. al, ICML 2017
80. 80
[Liu+ 2017] “Video Frame Synthesis using Deep Voxel Flow”,
Z. Liu, and et al., ICCV 2017
[Zhou+ 2017] “Unsupervised Learning of Depth and Ego-
Motion from Video”, T. Zhou, and et al., CVPR 2017
[Minh+ 2007] A. Minh and et al., “Three new graphical
models for statistical language modelling”, ICML 2007
[Arora+ 2015] RAND-WALK: A Latent Variable Model Approch
to Word Embeddings, S. Arora and et. al.
[Ferrer-i-Cancho+ 2017] The origins of Zipf's meaning-
frequency law, R. Ferrer-i-Cancho and et. al.